docs: add comprehensive Model Card for MatchFormer (ACCV 2022)

README.md

@@ -0,0 +1,105 @@
+---
+pipeline_tag: feature-matching
+library_name: pytorch
+license: apache-2.0
+tags:
+- transformer
+- feature-matching
+- accv-2022
+- vision
+- scannet
+- megadepth
+datasets:
+- scannet
+- megadepth
+---
+
+# MatchFormer: Interleaving Attention in Transformers for Feature Matching (ACCV 2022)
+
+Official model checkpoints for **MatchFormer: Interleaving Attention in Transformers for Feature Matching** (ACCV 2022 Oral).
+
+<div align="center">
+
+[![Paper](https://img.shields.io/badge/arXiv-2203.09645-B31B1B.svg)](https://arxiv.org/abs/2203.09645)
+[![GitHub](https://img.shields.io/badge/GitHub-MatchFormer-181717.svg?logo=github)](https://github.com/InSAI-Lab/MatchFormer)
+[![Collection](https://img.shields.io/badge/HF-Collection-FFD21E.svg)](https://huggingface.co/collections/InSAI-Lab)
+
+</div>
+
+---
+
+## 📌 Introduction
+
+In this work, we propose a novel hierarchical extract-and-match transformer, termed **MatchFormer**. Inside each stage of the hierarchical encoder, we interleave self-attention for feature extraction and cross-attention for feature matching, enabling an intuitive and powerful **extract-and-match** scheme. MatchFormer establishes robust and accurate dense correspondences across diverse indoor and outdoor challenging scenes.
+
+![MatchFormer Architecture](https://raw.githubusercontent.com/InSAI-Lab/MatchFormer/main/matchformer.png)
+
+---
+
+## 📂 Model Zoo & File Structure
+
+```text
+InSAI-Lab/MatchFormer
+├── indoor-large-SEA.ckpt    # Indoor large model with SEA (Spatial-Entropy Attention) (89.5 MB)
+├── indoor-lite-LA.ckpt      # Indoor lightweight model with LA (Linear Attention) (77.4 MB)
+├── outdoor-large-LA.ckpt    # Outdoor large model with LA (77.4 MB)
+└── outdoor-lite-SEA.ckpt    # Outdoor lightweight model with SEA (103.5 MB)
+```
+
+---
+
+## 📊 Benchmark Results
+
+### 1. Indoor Relative Pose Estimation on ScanNet (AUC)
+
+| Model | Backbone | Resolution | AUC @ 5° | AUC @ 10° | AUC @ 20° | Weights |
+| :--- | :--- | :---: | :---: | :---: | :---: | :--- |
+| **MatchFormer-Large** | largesea | (8, 2) | **43.3** | **63.4** | **77.1** | [`indoor-large-SEA.ckpt`](https://huggingface.co/InSAI-Lab/MatchFormer/resolve/main/indoor-large-SEA.ckpt) |
+| **MatchFormer-Lite** | litela | (8, 4) | **38.8** | **59.2** | **74.0** | [`indoor-lite-LA.ckpt`](https://huggingface.co/InSAI-Lab/MatchFormer/resolve/main/indoor-lite-LA.ckpt) |
+
+### 2. Outdoor Relative Pose Estimation on MegaDepth (AUC)
+
+| Model | Backbone | Resolution | AUC @ 5° | AUC @ 10° | AUC @ 20° | Weights |
+| :--- | :--- | :---: | :---: | :---: | :---: | :--- |
+| **MatchFormer-Large** | largela | (8, 2) | **53.3** | **69.7** | **81.8** | [`outdoor-large-LA.ckpt`](https://huggingface.co/InSAI-Lab/MatchFormer/resolve/main/outdoor-large-LA.ckpt) |
+| **MatchFormer-Lite** | litesea | (8, 4) | **48.2** | **65.1** | **78.4** | [`outdoor-lite-SEA.ckpt`](https://huggingface.co/InSAI-Lab/MatchFormer/resolve/main/outdoor-lite-SEA.ckpt) |
+
+---
+
+## ⚡ Quick Download Guide
+
+### Option 1: Hugging Face CLI
+
+```bash
+# Download all MatchFormer weights to model/weights/
+hf download InSAI-Lab/MatchFormer --local-dir model/weights
+
+# Or download a specific checkpoint
+hf download InSAI-Lab/MatchFormer indoor-large-SEA.ckpt --local-dir model/weights
+```
+
+### Option 2: Python `huggingface_hub`
+
+```python
+from huggingface_hub import hf_hub_download
+
+# Download indoor large SEA checkpoint
+ckpt_path = hf_hub_download(
+    repo_id="InSAI-Lab/MatchFormer",
+    filename="indoor-large-SEA.ckpt",
+    local_dir="model/weights"
+)
+```
+
+---
+
+## 📖 Citation
+
+```bibtex
+@inproceedings{wang2022matchformer,
+  title={MatchFormer: Interleaving Attention in Transformers for Feature Matching},
+  author={Wang, Qing and Zhang, Jiaming and Yang, Kailun and Peng, Kunyu and Stiefelhagen, Rainer},
+  booktitle={Asian Conference on Computer Vision (ACCV)},
+  year={2022}
+}
+```